AI-Based Intelligent Planning Method for the Lifting Construction Path of Steel Structures

Abstract

The present invention relates to an intelligent planning method for the lifting construction path of steel structures based on AI, belonging to the technical field of steel structure building construction, and includes the following operating steps: The first step: Establish a grid lifting database of steel structures. The second step: Abstract a steel structure weight map according to grid coordinates and weights. The third step: Based on factors such as the lower structure, the shape of the grid, and the height difference of the grid, combined with the steel structure weight map, conduct an all-element intelligent zoning of the steel structure. The fourth step: Combine the AI model, the steel structure lifting database, and the intelligent algorithm, and at the same time incorporate existing construction data to establish an AI database to intelligently plan the steel structure lifting construction path. Combine the AI model, the steel structure lifting database, and the intelligent algorithm, consider the existing construction data, and intelligently determine the steel structure zoning and plan the lifting construction path. Solve the problems that the existing steel structure zoning and the steel structure lifting construction path mainly rely on experience, the scheme design is slow, and the economy is not high.

Description

Technical Field

[0001] The present invention relates to the technical field of steel structure building construction, and particularly relates to an intelligent planning method for the construction path of steel structure lifting based on AI. Background Art

[0002] The stress state of a steel structure during the construction stage is affected by many uncertain factors, and the situation is more complex and changeable. Unreasonable setting of lifting points during the hoisting process, sudden changes in internal forces of structural members during hoisting, turning over, and installation in place, and uneven lowering of jacks during the unloading process of temporary structures, etc., will all cause non-uniform deformation of the overall structure. The resulting internal force redistribution will cause sudden changes in internal forces of some members or the collapse of temporary structures due to excessive loads. In addition, the non-synchronization during the traction and sliding process will also lead to uneven structural traction force and deviation of the structure. The unstable traction process will quickly cause the structure to vibrate under dynamic loads, and problems such as uneven track and mechanical problems will all cause changes in internal forces of structural members, and thus may cause damage to structural members.

[0003] The invention patent "A Construction Analysis Method for Hoisting and Unloading of Complex Large-Span Space Steel Structures", with the application number CN202211195652.6, discloses that based on theoretical analysis and numerical simulation, the whole process simulation and determination of the hoisting, unloading, and monitoring construction plans for complex large-span space steel structures are carried out. The influence of member segmentation, hoisting sequence, and temperature stress during the hoisting construction process is comprehensively considered, and the influence of unloading sequence and unloading control method during the unloading construction process is also considered. At the same time, a reasonable and effective monitoring plan is formulated for the complexity and uncertainty of actual construction, which can effectively improve the construction efficiency of subsequent complex large-span space steel structures, ensure construction safety, and solve the potential safety hazard problems caused by the large difference between the member stress and deformation during the construction process of large-span space steel structures and the design state due to the complexity of the structural form, construction technology, and process.

[0004] Steel structure zoning and construction path selection are crucial in steel structure construction. It divides the complex steel structure into multiple zones according to factors such as the weight, shape, and size of the steel structure, facilitating construction. During the actual construction process, reasonable steel structure zoning can effectively reduce the construction difficulty and improve the construction efficiency. By analyzing the steel structure, the boundaries and construction paths of each zone are determined to ensure that each zone can maintain its structural form during independent construction, control costs, and improve the overall project quality.

[0005] The existing steel structure zoning and construction path selection mainly rely on the experience of construction personnel. The steel structure is initially divided according to shape symmetry and structural particularity, and then the construction path is determined according to construction experience. Summary of the Invention

[0006] The present invention mainly solves the deficiencies existing in the prior art, and provides an intelligent planning method for the lifting construction path of steel structures based on AI. By abstracting the steel structure weight topographic map, it intelligently divides the steel structure into zones, and considering factors such as the lower structure, the shape of the steel structure, and the height difference of the steel structure, combined with the steel structure weight topographic map, it comprehensively corrects the steel structure zoning method to solve the problem that the existing steel structure zoning mainly relies on experience. By combining the AI model, the steel structure lifting database and the intelligent algorithm, considering the existing construction data, it intelligently determines the steel structure zoning and plans the lifting construction path. It solves the problems that the existing steel structure lifting construction path mainly relies on experience, the scheme design is slow, and the economy is not high.

[0007] The above technical problems of the present invention are mainly solved by the following technical solutions:

[0008] An intelligent planning method for the lifting construction path of steel structures based on AI, including the following operation steps:

[0009] The first step: Establish a grid lifting database for the steel structure.

[0010] The second step: According to the grid coordinates and weights, abstract the steel structure weight topographic map.

[0011] The third step: Based on factors such as the lower structure, the shape of the grid and the height difference of the grid, combined with the steel structure weight topographic map, conduct comprehensive element intelligent zoning of the steel structure.

[0012] The fourth step: Use the combination of the AI model, the steel structure lifting database and the intelligent algorithm, and at the same time incorporate the existing construction data to establish an AI database to intelligently plan the steel structure lifting construction path.

[0013] Preferably, the grid lifting database is based on the construction data of existing steel structure projects to establish a steel structure lifting database, including data such as the size of the lifted steel structure, the weight of the lifted steel structure, the number of lifting suspension points of the steel structure, lifting deformation, stress ratio and the construction cost of steel structure lifting.

[0014] Preferably, the abstract steel structure weight topographic map takes the steel structure cell as the basic unit, stores the numbers and weights of each member, and stores the numbers and weights of each member. If the label of cell 1 is D1, then the labels of the members forming cell 1 are D1-1, D1-2, D1-3 in sequence, and the weights are M1-1, M1-2, M1-3; the label of the adjacent cell 2 is D2, and the labels of the members forming cell 2 are D2-1, D2-2, D2-3 in sequence, and the weights are M2-1, M2-2, M2-3; and so on for the remaining cells; extract the X and Y coordinate points of the upper chord nodes of the steel structure to form the steel structure plane topographic map, take the closed figure surrounded by the upper chord members as the topographic map unit, and assign the cell weights within the projected area of the topographic map unit to the corresponding topographic map unit to form the steel structure weight topographic map.

[0015] Preferably, to correct the influence of the lower structure on the steel structure weight topographic map, considering that there are support columns or shaped columns at the lower part of the steel structure, the weights of the support columns or shaped columns are evenly superimposed on the corresponding topographic map range units; to correct the influence of the shape on the steel structure weight topographic map, for a steel structure with a strange and irregular shape, traverse the outermost points at the top, bottom, left, and right of the ring steel structure. Taking each outermost point as a reference, form a closed rectangle that includes the outer shape of the steel structure. The closed figure formed by the rectangle's edge and the steel structure's edge is divided into several topographic map units with a side length of 1 unit length. Each topographic map unit is named E1, E2, E3 in sequence, and its weight is given as 0, which is called a zero-weight topographic map cell.

[0016] Preferably, taking the centroid of the rectangular steel structure weight topographic map as the origin, form an outer-expanded quadrilateral similar to the rectangular steel structure weight topographic map. Through the traversal algorithm, continuously expand it. When there is a zero-weight topographic map cell inside the outer-expanded quadrilateral, the outer-expanded quadrilateral stops expanding, and check whether the vertices of the outer-expanded quadrilateral are located inside the zero-weight topographic map cell. If it is located inside the zero-weight topographic map cell, the outer-expanded quadrilateral stops expanding; if it is located inside a non-zero-weight topographic map cell, the short side part of the outer-expanded quadrilateral stops expanding, and the long side part continues to expand until the vertices of the outer-expanded quadrilateral are located inside the zero-weight topographic map cell.

[0017] Preferably, taking the outer contour of the outer-expanded quadrilateral as the boundary, name the non-zero-weight closed independent regions outside the outer-expanded quadrilateral as F regions; inside the outer-expanded quadrilateral, according to the steel structure weight topographic map, name the regions with an average weight difference greater than δ as S regions. According to the size of δ, intelligently distinguish the single-layer grid structure, double-layer grid structure, and other structural forms with weight differences in the complex steel structure, and then intelligently divide the regions. Name the other regions as P regions.

[0018] Preferably, traverse the Z coordinates of the steel structure nodes to obtain the height difference of the steel structure, and divide the steel structure according to the following rules:

[0019] If the height difference of the steel structure is small, then: 1) Evenly divide the steel structure along the long side direction of the quadrilateral; 2) Evenly divide the steel structure along the short side direction of the quadrilateral; 3) Divide the steel structure along both the long and short side directions at the same time.

[0020] If the height difference of the steel structure is large, determine whether there is more than one height maximum point. If not, take the topmost point of the steel structure as the center: 1) Oddly divide the steel structure along the long side direction of the quadrilateral; 2) Oddly divide the steel structure along the short side direction of the quadrilateral; 3) Divide the steel structure along both the long and short side directions at the same time. If there is more than one height maximum point, first divide the larger area with the height minimum point, and then perform zoning according to the zoning method for more than one height maximum point.

[0021] Respectively with Fij , S ij , P ij Name each steel structure partition in sequence, where F ij , S ij , P ij respectively represent the steel structure partitions in the i-th row and j-th column of the F, S, and P areas.

[0022] Preferably, utilize the steel structure lifting database, select the characteristics that have a greater impact on the steel structure lifting construction cost, such as deformation, stress ratio, steel structure size, weight, and the number of lifting points, to train the preset AI model; by adjusting the hyperparameters of the AI model, obtain the optimal steel structure lifting AI model; the main function of the steel structure lifting AI model is to evaluate and predict the construction cost of each sub-item of the steel structure partition based on the influencing characteristics of the steel structure size, weight, and the number of lifting points.

[0023] Preferably, based on the trained steel structure lifting AI model, evaluate the deformation, stress ratio, total construction cost, and the construction cost of the partition measures of the divided steel structure partitions according to the rules; utilize the genetic algorithm combined with the steel structure lifting AI model, adopt the flowing water construction technology, and on the basis of meeting the specified deformation and stress ratio, optimize the top three partition forms and construction paths with the minimum total construction cost as the control index; the single-step construction cost is the construction cost of this step minus the construction measure cost available for this step in the previous step, and the selected block in the latter construction step is at least one block away from the selected block in the previous construction step; the fitness function is as shown in Equation 1, where B k+1 is the construction cost of the (k + 1)-th construction step, and C k is the construction measure cost available for the (k + 1)-th construction step in the k-th construction step;

[0024] Equation (1).

[0025] For steel structures with a large height difference, the first construction step is to lift the highest part in blocks, and the lifting construction is accumulated in sequence according to the height. For steel structures with a small height difference, randomly select ≥1 blocks to start lifting.

[0026] Preferably, when the genetic algorithm combines with the steel structure to improve the AI model to determine the partition size and quantity, each time the number of divided blocks is adjusted, according to the steel structure division method, the steel structure partitions are renamed in sequence until the optimal partition size and quantity are confirmed; when optimizing the optimal construction path, each construction step outputs the selected steel structure partition name, and the construction path can be confirmed according to the construction step and the partition name; based on the three selected partition forms and construction paths, a multi-objective genetic algorithm is selected, with the docking accuracy between the rod joints of each partition as the control index, considering the overall force and deformation of the structure with the minimum structural strain energy, the positions of the hoisting points and support frames of the steel structure partitions are intelligently arranged for further optimization; the partition form and construction path with high economic benefits and small docking accuracy are selected; the fitness function is as shown in Equation 2:

[0027] Equation (2).

[0028] In the formula: BIAS is the deformation size of the partition docking point, Di,j is the deformation size of the jth docking point in the ith partition; energy is the overall structural strain energy.

[0029] The present invention can achieve the following effects:

[0030] The present invention provides an intelligent planning method for the construction path of steel structure hoisting based on AI. Compared with the prior art, by abstracting the steel structure weight topographic map, the steel structure is intelligently partitioned, and considering factors such as the lower structure, the shape of the steel structure, and the height difference of the steel structure, combined with the steel structure weight topographic map, the steel structure partition method is comprehensively corrected to solve the problem that the existing steel structure partition mainly relies on experience. By combining the AI model, the steel structure hoisting database and the intelligent algorithm, considering the existing construction data, the steel structure partition is intelligently determined and the hoisting construction path is planned. Solve the problems that the existing steel structure hoisting construction path mainly relies on experience, the scheme design is slow, and the economy is not high.

[0031] It has the following advantages:

[0032] 1. It improves the scientificity and accuracy of steel structure partition and hoisting construction path selection, and avoids the limitations of manual experience methods.

[0033] 2. It improves the economy of steel structure partition and hoisting construction path selection. Based on construction factors, with economy as the control index, the size of the steel structure partition is determined and the partition construction path is planned.

[0034] 3. It improves the planning efficiency of the steel structure hoisting construction path. By using the method of combining intelligent algorithms, the steel structure hoisting database and AI, the steel structure hoisting construction path can be quickly planned.

[0035] 4. It is applicable not only to regular-shaped steel structures but also to special-shaped steel structures.

[0036] 5. It is applicable not only to steel structures with a single structural form but also to steel structures with a complex structural form composed of multiple structures. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The technical solution of the invention will be further specifically described below through embodiments in conjunction with the accompanying drawings.

[0039] Embodiment 1: As Figure 1 shown, an intelligent planning method for the lifting construction path of a steel structure based on AI includes the following operating steps:

[0040] The first step: Establish a grid lifting database for the steel structure. The grid lifting database is based on the existing construction data of steel structure projects to establish a steel structure lifting database, including data on the size of the lifted steel structure, the weight of the lifted steel structure, the number of lifting suspension points of the steel structure, lifting deformation, stress ratio, and the construction cost of steel structure lifting.

[0041] The second step: According to the grid coordinates and weight, abstract a topographic map of the steel structure weight.

[0042] The abstract topographic map of the steel structure weight takes the steel structure cell as the basic unit, stores the numbers and weights of each member. If the label of cell 1 is D1, the labels of the members forming cell 1 are D1-1, D1-2, D1-3 in sequence, and the weights are M1-1, M1-2, M1-3; the label of the adjacent cell 2 is D2, the labels of the members forming cell 2 are D2-1, D2-2, D2-3 in sequence, and the weights are M2-1, M2-2, M2-3; and so on for the remaining cells; extract the X and Y coordinate points of the upper chord nodes of the steel structure to form a plane topographic map of the steel structure. Taking the closed figure surrounded by the upper chord members as the topographic map unit, assign the weight of the cells within the projected area of the topographic map unit to the corresponding topographic map unit to form a topographic map of the steel structure weight.

[0043] The third step: Based on factors such as the lower structure, the shape of the grid, and the height difference of the grid, combined with the topographic map of the steel structure weight, perform intelligent zoning of the steel structure with all elements.

[0044] Correct the influence of the lower structure on the steel structure weight topographic map. When there are support columns or shaped columns at the lower part of the steel structure, the weights of the support columns or shaped columns are evenly superimposed on the corresponding topographic map range units; correct the influence of the shape on the steel structure weight topographic map. For steel structures with strange and irregular shapes, traverse the outermost, bottommost, leftmost, and rightmost protruding points of the ring-shaped steel structure. Taking each protruding point as a reference, form a closed rectangle that includes the outer shape of the steel structure. The closed figure formed by the rectangle edge and the steel structure edge is divided into several topographic map units with a side length of 1 unit length. Each topographic map unit is named E1, E2, E3 in turn, and its weight is given as 0, which is called a zero-weight topographic map cell.

[0045] Taking the centroid of the rectangular steel structure weight topographic map as the origin, form an outer-expanded quadrilateral similar to the rectangular steel structure weight topographic map. Through the traversal algorithm, continuously expand it. When there are zero-weight topographic map cells in the outer-expanded quadrilateral, the outer-expanded quadrilateral stops expanding, and check whether the vertices of the outer-expanded quadrilateral are located in the zero-weight topographic map cells. If it is located in the zero-weight topographic map cell, the outer-expanded quadrilateral stops expanding; if it is located in a non-zero-weight topographic map cell, the short side part of the outer-expanded quadrilateral stops expanding, and the long side part continues to expand until the vertices of the outer-expanded quadrilateral are located in the zero-weight topographic map cell.

[0046] Taking the outer contour of the outer-expanded quadrilateral as the boundary, name the non-zero-weight closed independent regions outside the outer-expanded quadrilateral as F regions; inside the outer-expanded quadrilateral, according to the steel structure weight topographic map, name the regions with an average weight difference greater than δ as S regions, and intelligently distinguish the single-layer grid structure, double-layer grid structure and other structural forms with weight differences in the complex steel structure according to the size of δ, and then intelligently divide the regions, and name other regions as P regions.

[0047] Traverse the Z coordinates of the steel structure nodes to obtain the height difference of the steel structure, and divide the steel structure according to the following rules:

[0048] If the height difference of the steel structure is small, then: 1) Divide the steel structure evenly along the long side direction of the quadrilateral; 2) Divide the steel structure evenly along the short side direction of the quadrilateral; 3) Divide the steel structure evenly along both the long and short side directions at the same time.

[0049] If the height difference of the steel structure is large, judge whether there is more than one height maximum point. If not, take the topmost point of the steel structure as the center: 1) Divide the steel structure unevenly along the long side direction of the quadrilateral; 2) Divide the steel structure unevenly along the short side direction of the quadrilateral; 3) Divide the steel structure unevenly along both the long and short side directions at the same time. If there is more than one height maximum point, first divide the larger area with the height minimum point, and then divide the area according to the zoning method when there is more than one height maximum point.

[0050] Respectively with F ij 、S ij 、P ijName each steel structure partition in sequence, where F ij 、S ij 、P ij respectively represent the steel structure partitions in the i-th row and j-th column of the F, S, and P areas.

[0051] Step 4: Combine the AI model, the steel structure lifting database, and the intelligent algorithm, and at the same time integrate the existing construction data to establish an AI database to intelligently plan the steel structure lifting construction path.

[0052] Utilize the steel structure lifting database to select the characteristics that have a greater impact on the steel structure lifting construction cost, such as deformation, stress ratio, steel structure size, weight, and the number of lifting points, and train the preset AI model; by adjusting the hyperparameters of the AI model, obtain the optimal steel structure lifting AI model; the main function of the steel structure lifting AI model is to evaluate and predict the construction cost of each sub-item of the steel structure partition based on the influencing characteristics of the steel structure size, weight, and the number of lifting points.

[0053] Based on the trained steel structure lifting AI model, evaluate the deformation, stress ratio, total construction cost, and the construction cost of measures available for other partitions of the planned steel structure partition according to the rules; utilize the genetic algorithm combined with the steel structure lifting AI model, adopt the flow construction process, and on the basis of meeting the specified deformation and stress ratio, take the minimum total construction cost as the control index to optimize the top three partition forms and construction paths with the minimum total construction cost; the single-step construction cost is the construction cost of this step minus the construction measure cost available for this step in the previous step, and the selected block in the latter construction step is at least one block away from the selected block in the previous construction step; the fitness function is as shown in Equation 1, where B k+1 is the construction cost of the (k + 1)-th construction step, and C k is the construction measure cost available for the (k + 1)-th construction step in the k-th construction step;

[0054] Equation (1);

[0055] For steel structures with a large height difference, the first construction step is to lift the highest-scoring block by height, and the lifting construction is accumulated in sequence by height. For steel structures with a small height difference, randomly select ≥1 block to start lifting.

[0056] When the genetic algorithm combines with the steel structure to improve the AI model to determine the partition size and quantity, every time the number of blocks is adjusted, according to the steel structure division method, the steel structure partitions are renamed in sequence until the optimal partition size and quantity are confirmed; when optimizing the optimal construction path, the selected steel structure partition name is output for each construction step, and the construction path can be confirmed according to the construction step and the partition name; based on the three selected partition forms and construction paths, the multi-objective genetic algorithm is selected, with the docking accuracy between the rod joints of each partition as the control index, and the minimum structural strain energy is considered to take into account the overall force and deformation of the structure, and the positions of the lifting points and support frames of the steel structure partitions are intelligently arranged for re-optimization; the partition form and construction path with high economic benefits and small docking accuracy are selected; the fitness function is as shown in Equation 2:

[0057] Equation (2);

[0058] In the formula: BIAS is the deformation size of the partition docking point, Di,j is the deformation size of the jth docking point in the ith partition; energy is the overall structural strain energy.

[0059] To sum up, the intelligent planning method for the construction path of the steel structure based on AI intelligently partitions the steel structure by abstracting the steel structure weight topographic map, and considering factors such as the lower structure, the shape of the steel structure, and the height difference of the steel structure, combines with the steel structure weight topographic map, and comprehensively modifies the steel structure partition method to solve the problem that the existing steel structure partition mainly relies on experience. By combining the AI model, the steel structure lifting database and the intelligent algorithm, considering the existing construction data, the steel structure partition is intelligently determined and the lifting construction path is planned. Solve the problems that the existing steel structure lifting construction path mainly relies on experience, the scheme design is slow, and the economy is not high.

[0060] The above are only specific embodiments of the present invention, but the structural features of the present invention are not limited thereto. Any changes or modifications made by those skilled in the art within the scope of the present invention are covered by the patent scope of the present invention.

Claims

1. An AI-based intelligent planning method for steel structure lifting construction path, characterized in that The steps are as follows: Step 1: Establish a steel structure grid lifting database; Step 2: Make an abstract steel structure weight topographic map based on the grid coordinates and weight; The abstract steel structure weight topography uses the steel structure unit cell as the basic unit to store the number and corresponding weight of each bar; Extract the X and Y coordinate points of the upper chord nodes of the steel structure to form a plane topographic map of the steel structure. Take the closed figure surrounded by the upper chord members as the topographic map unit, assign the weight of the cell within the projection area of ​​the topographic map unit to the corresponding topographic map unit, and form a steel structure weight topographic map. Step 3: Based on the factors of the lower structure, grid shape and grid height difference, combined with the steel structure weight topography, all-element steel structure intelligent zoning is carried out; Taking the center of the rectangular steel structure weight topographic figure as the origin, an outward-expanding quadrilateral similar to the rectangular steel structure weight topographic figure is formed, and the outward-expanding quadrilateral is continuously expanded through the traversal algorithm. When there is a zero-weight topographic figure cell in the outward-expanding quadrilateral, the outward-expanding quadrilateral stops expanding, and detects whether the vertex of the outward-expanding quadrilateral is located in the zero-weight topographic figure cell; if it is located in the zero-weight topographic figure cell, the outward-expanding quadrilateral stops expanding; if it is located in a non-zero-weight topographic figure cell, the short side of the outward-expanding quadrilateral stops expanding, and the long side continues to expand until the vertex of the outward-expanding quadrilateral is located in the zero-weight topographic figure cell; The outer contour of the expanded quadrilateral is used as the boundary to enclose the non-zero weight areas outside the expanded quadrilateral; inside the expanded quadrilateral, the average weight difference of each area is compared with δ according to the steel structure weight topography, and the single-layer grid structure, double-layer grid structure and other structures with weight differences in the complex steel structure are intelligently distinguished according to the size of δ, and then the areas are intelligently divided and named; Traverse the Z coordinates of the steel structure nodes, obtain the height difference of the steel structure, and divide the steel structure according to the following rules; If the height difference of the steel structure is small, then: 1) divide the steel structure into an even number of equal parts along the long side of the quadrilateral; 2) divide the steel structure into an even number of equal parts along the short side of the quadrilateral; 3) divide the steel structure into equal parts along both the long and short sides; If the height difference of the steel structure is large, determine whether there is more than one maximum height point. If not, take the top of the steel structure as the center: 1) divide the steel structure into odd equal parts along the long side of the quadrilateral; 2) divide the steel structure into odd equal parts along the short side of the quadrilateral; 3) divide the steel structure into equal parts along the long and short sides at the same time; if there is more than one maximum height point, first divide the larger area by the minimum height point, and then divide it according to the partition method when there is more than one maximum height point; Step 4: Utilize the combination of AI models, steel structure improvement database and intelligent algorithms, and integrate existing construction data to establish an AI database to intelligently plan the steel structure improvement construction path.

2. The AI-based intelligent planning method for steel structure lifting construction path according to claim 1 is characterized by: The grid lifting database is based on the existing steel structure engineering construction data to establish a steel structure lifting database, including data on the size of the lifted steel structure, the weight of the lifted steel structure, the number of steel structure lifting points, lifting deformation, stress ratio and steel structure lifting construction costs.

3. The AI-based intelligent planning method for steel structure lifting construction path according to claim 1 is characterized by: Correct the influence of the lower structure on the weight topographic map of the steel structure. If there are supporting columns or modeling columns under the steel structure, the weight of the supporting columns or modeling columns will be evenly superimposed on the corresponding topographic map range unit; Correct the influence of shape on the weight map of steel structure. For steel structures with strange and irregular shapes, traverse the protruding points at the top, bottom, leftmost and rightmost parts of the ring steel structure, and use each protruding point as a reference to form a closed rectangle containing the outer shape of the steel structure. The closed figure formed by the edge of the rectangle and the edge of the steel structure is divided into several map units with a side length of unit length. The weight of each map unit is assigned to be 0, which is called a zero-weight map cell.

4. The AI-based intelligent planning method for steel structure lifting construction path according to claim 1 is characterized by: By using the steel structure lifting database, we selected the features that have a greater impact on the steel structure lifting construction cost, such as deformation, stress ratio, steel structure size, weight and number of lifting points, and trained the preset AI model; by adjusting the hyperparameters of the AI ​​model, we obtained the optimal steel structure lifting AI model; the function of the steel structure lifting AI model is to evaluate and predict the construction costs of each sub-item of the steel structure partition according to the influencing characteristics of the steel structure size, weight and number of lifting points.

5. The AI-based intelligent planning method for steel structure lifting construction path according to claim 4 is characterized in that: Based on the trained AI model for steel structure improvement, the deformation, stress ratio, total construction cost and construction cost of the partitioned steel structure measures are evaluated according to the rules; the genetic algorithm is combined with the AI ​​model for steel structure improvement, and the flow construction process is adopted. On the basis of meeting the deformation and stress ratio of the specifications, the total construction cost is minimized as the control index to optimize the first three partition forms and construction paths with the minimum total construction cost; the single-step construction cost is the construction cost of this step minus the construction cost of the previous step that can be used for this step, and the block selected for the next construction step is at least one block away from the block selected for the previous construction step; the fitness function is as shown in Formula 1, where B k+1 is the construction cost of the k+1th construction step, C k is the cost of construction measures in the kth construction step that can be used in the k+1th construction step; For steel structures with large height differences, the first construction step is to lift the block with the highest height, and then lift the blocks cumulatively in order of height. For steel structures with small height differences, randomly select blocks with a number ≥1 to start lifting.

6. The AI-based intelligent planning method for steel structure lifting construction path according to claim 5 is characterized by: When the genetic algorithm is combined with the steel structure improvement AI model to determine the partition size and number, each time the number of blocks is adjusted, the steel structure partitions are renamed in sequence according to the steel structure division method until the optimal partition size and number are confirmed; when optimizing the optimal construction path, the selected steel structure partition name is output for each construction step, and the construction path can be confirmed according to the construction step and partition name; based on the three selected partition forms and construction paths, a multi-objective genetic algorithm is selected, with the docking accuracy between the nodes of each partition bar as the control indicator, and the overall stress and deformation of the structure are considered with the minimum structural strain energy, and the steel structure partition hanging points and support frame positions are intelligently arranged for re-optimization; select the partition form and construction path with high economic benefits and low docking accuracy; the fitness function is as shown in Formula 2: Where: BIAS is the deformation size of the partition docking point, Di,j is the deformation size of the jth docking point in the i-th partition; energy is the overall strain energy of the structure.

Images